Skip to content

Benchmark

Arena ELO Vision Style-Controlled

People compare model answers and choose which they prefer. Higher scores are better.

Models measured
147
Scores recorded
168
Sources
1
IQ weight
1.56

Score distribution

1,187.6
Mean
1,215.3
Median
96.7
Std dev
1,025.4
10th percentile
1,287.8
90th percentile
881.3
Min
881.31,308.8
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.56 for chat models, measured over 147 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Fable 5High· LMArena data1,308.8
2Claude Fable 5.2Max· LMArena data1,305.3
3Claude Opus 4.7· LMArena data1,298.7
4Claude Opus 4.6High· LMArena data1,298.2
5Claude Opus 4.7High· LMArena data1,298
6Gemini 3.7 FlashHigh· LMArena data1,294.2
7Muse Spark· LMArena data1,294
8Qwen3.8 Max· LMArena data1,293.7
9Claude Opus 5.5High· LMArena data1,293.2
10Muse Spark 1.2xHigh· LMArena data1,293
11Claude Opus 4.6· LMArena data1,293
12Gemini 3.8 FlashHigh· LMArena data1,292.8
13GPT-6.1 SolMax· LMArena data1,289.9
14Claude Fable 5.1Max· LMArena data1,289.8
15Gemini 3 Pro Preview· LMArena data1,289.1
16Muse Spark 1.3Max· LMArena data1,288.2
17GPT-5.6 SolxHigh· LMArena data1,288.1
18Muse Spark 1.3xHigh· LMArena data1,287.8
19Claude Opus 4.8High· LMArena data1,285.5
20Claude Opus 5High· LMArena data1,285.3
21GPT 5.5· LMArena data1,284.8
22GPT 5.5High· LMArena data1,283.9
23Gemini 3.5 FlashMedium· LMArena data1,282.1
24GPT 5.4High· LMArena data1,282
25Gemini 3.5 FlashHigh· LMArena data1,281.1
26GPT-6 AstraMax· LMArena data1,281
27Gemini 3.1 Pro Preview· LMArena data1,280.4
28Grok 4.5· LMArena data1,280.3
29Gemini 3.6 FlashHigh· LMArena data1,280
30Muse Spark 1.1· LMArena data1,278.9
31Claude Opus 4.8· LMArena data1,278.1
32GPT-5.5 Instant· LMArena data1,277.7
33GPT-5.2 Chat20260210· LMArena data1,277.5
34GPT 5.4· LMArena data1,277.3
35Claude Sonnet 4.6· LMArena data1,274.7
36GLM 5.3 Flash· LMArena data1,273.8
37Gemini 3 Flash· LMArena data1,272.2
38GPT-5.6 TerraxHigh· LMArena data1,267.1
39Gemini 3.5 Flash Lite· LMArena data1,265.9
40Kimi K2.6· LMArena data1,264.7
41Gemma 4 31B IT· LMArena data1,264.7
42Grok 4.6High· LMArena data1,264.3
43Claude Sonnet 5.5xHigh· LMArena data1,264.2
44GPT-6.1 TerraMax· LMArena data1,263
45Qwen3.7 Plus· LMArena data1,262.4
46DeepSeek V4.1 Flash 0910Max· LMArena data1,262.2
47Claude Sonnet 5High· LMArena data1,260.8
48Gemini 3 FlashMinimal· LMArena data1,259.8
49GPT-6 SolMax· LMArena data1,257.5
50Doubao Seed 2.0 Pro· LMArena data1,256.4

Showing 1–50 of 168 results.

Data credits: LMArena, CC BY 4.0 (licence)